diff mbox series

[RFC,05/20] dev_dax_iomap: Add dax_operations for use by fs-dax on devdax

Message ID 5727b1be956278e3a6c4cf7b728ee4f8f037ae51.1708709155.git.john@groves.net
State Superseded
Headers show
Series Introduce the famfs shared-memory file system | expand

Commit Message

John Groves Feb. 23, 2024, 5:41 p.m. UTC
Notes about this commit:

* These methods are based somewhat loosely on pmem_dax_ops from
  drivers/nvdimm/pmem.c

* dev_dax_direct_access() is returns the hpa, pfn and kva. The kva was
  newly stored as dev_dax->virt_addr by dev_dax_probe().

* The hpa/pfn are used for mmap (dax_iomap_fault()), and the kva is used
  for read/write (dax_iomap_rw())

* dev_dax_recovery_write() and dev_dax_zero_page_range() have not been
  tested yet. I'm looking for suggestions as to how to test those.

Signed-off-by: John Groves <john@groves.net>
---
 drivers/dax/bus.c | 107 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 107 insertions(+)

Comments

Jonathan Cameron Feb. 26, 2024, 12:32 p.m. UTC | #1
On Fri, 23 Feb 2024 11:41:49 -0600
John Groves <John@Groves.net> wrote:

> Notes about this commit:
> 
> * These methods are based somewhat loosely on pmem_dax_ops from
>   drivers/nvdimm/pmem.c
> 
> * dev_dax_direct_access() is returns the hpa, pfn and kva. The kva was
>   newly stored as dev_dax->virt_addr by dev_dax_probe().
> 
> * The hpa/pfn are used for mmap (dax_iomap_fault()), and the kva is used
>   for read/write (dax_iomap_rw())
> 
> * dev_dax_recovery_write() and dev_dax_zero_page_range() have not been
>   tested yet. I'm looking for suggestions as to how to test those.
> 
> Signed-off-by: John Groves <john@groves.net>
> ---
>  drivers/dax/bus.c | 107 ++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 107 insertions(+)
> 
> diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
> index 664e8c1b9930..06fcda810674 100644
> --- a/drivers/dax/bus.c
> +++ b/drivers/dax/bus.c
> @@ -10,6 +10,12 @@
>  #include "dax-private.h"
>  #include "bus.h"
>  
> +#if IS_ENABLED(CONFIG_DEV_DAX_IOMAP)
> +#include <linux/backing-dev.h>
> +#include <linux/pfn_t.h>
> +#include <linux/range.h>
> +#endif
> +

Is it worth avoiding includes based on config? Probably not.

>  static DEFINE_MUTEX(dax_bus_lock);
>  
>  #define DAX_NAME_LEN 30
> @@ -1349,6 +1355,101 @@ __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
>  }
>  EXPORT_SYMBOL_GPL(dax_pgoff_to_phys);
>  
> +#if IS_ENABLED(CONFIG_DEV_DAX_IOMAP)
> +

> +
> +static long __dev_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
> +			     long nr_pages, enum dax_access_mode mode, void **kaddr,
> +			     pfn_t *pfn)
> +{
> +	struct dev_dax *dev_dax = dax_get_private(dax_dev);
> +	size_t dax_size = dev_dax_size(dev_dax);
> +	size_t size = nr_pages << PAGE_SHIFT;
> +	size_t offset = pgoff << PAGE_SHIFT;
> +	phys_addr_t phys;
> +	u64 virt_addr = dev_dax->virt_addr + offset;
> +	pfn_t local_pfn;
> +	u64 flags = PFN_DEV|PFN_MAP;
> +
> +	WARN_ON(!dev_dax->virt_addr); /* virt_addr must be saved for direct_access */
Fair enough, but from local code point of view, does it make sense to check this
if !kaddr as we won't use this.
> +
> +	phys = dax_pgoff_to_phys(dev_dax, pgoff, nr_pages << PAGE_SHIFT);
> +
> +	if (kaddr)
> +		*kaddr = (void *)virt_addr;

Back to earlier comment on virt_addr as a void *. Definitely looking like
that would be more accurate and simpler!  Also not much point in computing
virt_addr unless kaddr is good.

> +
> +	local_pfn = phys_to_pfn_t(phys, flags); /* are flags correct? */
If you aren't going to do anything with it for !pfn, move it under the if (pfn).

> +	if (pfn)
> +		*pfn = local_pfn;
> +
> +	/* This the valid size at the specified address */
> +	return PHYS_PFN(min_t(size_t, size, dax_size - offset));
> +}
> +

> +
> +static const struct dax_operations dev_dax_ops = {
> +	.direct_access = dev_dax_direct_access,
> +	.zero_page_range = dev_dax_zero_page_range,
> +	.recovery_write = dev_dax_recovery_write,
> +};
> +
> +#endif /* IS_ENABLED(CONFIG_DEV_DAX_IOMAP) */
> +
>  struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
>  {
>  	struct dax_region *dax_region = data->dax_region;
> @@ -1404,11 +1505,17 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
>  		}
>  	}
>  

If we were to make this 

	if (IS_ENABLED(CONFIG_DEV_DAX_IOMAP))

etc can we avoid the ifdef stuff above and let dead code removal deal with it?
Might need a few stubs - I haven't tried.

> +#if IS_ENABLED(CONFIG_DEV_DAX_IOMAP)
> +	/* holder_ops currently populated separately in a slightly hacky way */
> +	dax_dev = alloc_dax(dev_dax, &dev_dax_ops);
> +#else
>  	/*
>  	 * No dax_operations since there is no access to this device outside of
>  	 * mmap of the resulting character device.
>  	 */
>  	dax_dev = alloc_dax(dev_dax, NULL);
> +#endif
> +
>  	if (IS_ERR(dax_dev)) {
>  		rc = PTR_ERR(dax_dev);
>  		goto err_alloc_dax;
John Groves Feb. 26, 2024, 4:09 p.m. UTC | #2
On 24/02/26 12:32PM, Jonathan Cameron wrote:
> On Fri, 23 Feb 2024 11:41:49 -0600
> John Groves <John@Groves.net> wrote:
> 
> > Notes about this commit:
> > 
> > * These methods are based somewhat loosely on pmem_dax_ops from
> >   drivers/nvdimm/pmem.c
> > 
> > * dev_dax_direct_access() is returns the hpa, pfn and kva. The kva was
> >   newly stored as dev_dax->virt_addr by dev_dax_probe().
> > 
> > * The hpa/pfn are used for mmap (dax_iomap_fault()), and the kva is used
> >   for read/write (dax_iomap_rw())
> > 
> > * dev_dax_recovery_write() and dev_dax_zero_page_range() have not been
> >   tested yet. I'm looking for suggestions as to how to test those.
> > 
> > Signed-off-by: John Groves <john@groves.net>
> > ---
> >  drivers/dax/bus.c | 107 ++++++++++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 107 insertions(+)
> > 
> > diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
> > index 664e8c1b9930..06fcda810674 100644
> > --- a/drivers/dax/bus.c
> > +++ b/drivers/dax/bus.c
> > @@ -10,6 +10,12 @@
> >  #include "dax-private.h"
> >  #include "bus.h"
> >  
> > +#if IS_ENABLED(CONFIG_DEV_DAX_IOMAP)
> > +#include <linux/backing-dev.h>
> > +#include <linux/pfn_t.h>
> > +#include <linux/range.h>
> > +#endif
> > +
> 
> Is it worth avoiding includes based on config? Probably not.

Just trying to demonstrate that I can be tedious :D
I'll drop the #if unless somebody disagrees.

> 
> >  static DEFINE_MUTEX(dax_bus_lock);
> >  
> >  #define DAX_NAME_LEN 30
> > @@ -1349,6 +1355,101 @@ __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
> >  }
> >  EXPORT_SYMBOL_GPL(dax_pgoff_to_phys);
> >  
> > +#if IS_ENABLED(CONFIG_DEV_DAX_IOMAP)
> > +
> 
> > +
> > +static long __dev_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
> > +			     long nr_pages, enum dax_access_mode mode, void **kaddr,
> > +			     pfn_t *pfn)
> > +{
> > +	struct dev_dax *dev_dax = dax_get_private(dax_dev);
> > +	size_t dax_size = dev_dax_size(dev_dax);
> > +	size_t size = nr_pages << PAGE_SHIFT;
> > +	size_t offset = pgoff << PAGE_SHIFT;
> > +	phys_addr_t phys;
> > +	u64 virt_addr = dev_dax->virt_addr + offset;
> > +	pfn_t local_pfn;
> > +	u64 flags = PFN_DEV|PFN_MAP;
> > +
> > +	WARN_ON(!dev_dax->virt_addr); /* virt_addr must be saved for direct_access */
> Fair enough, but from local code point of view, does it make sense to check this
> if !kaddr as we won't use this.

Hmm. This gets called with kaddr=NULL for mmap faults, and with non-NULL
kaddr for read/write (which need the virt_addr to do a memcpy variant).
If dev_dax->virt-addr is NULL, mmap will work but read/write will hork.

I lean toward keeping the warning. With these updates, it's broken if
read/write are broken.

> > +
> > +	phys = dax_pgoff_to_phys(dev_dax, pgoff, nr_pages << PAGE_SHIFT);
> > +
> > +	if (kaddr)
> > +		*kaddr = (void *)virt_addr;
> 
> Back to earlier comment on virt_addr as a void *. Definitely looking like
> that would be more accurate and simpler!  Also not much point in computing
> virt_addr unless kaddr is good.

Yes, done (the void *).

the computation is copied directly from drivers/nvdimm/__pmem_direct_access() -
which does not warn if virt_addr is null. Actually I suppose this code should
just trust that dev_dax_probe sets virt_addr, and not warn?

So I'm now contradicting myself above...

> 
> > +
> > +	local_pfn = phys_to_pfn_t(phys, flags); /* are flags correct? */
> If you aren't going to do anything with it for !pfn, move it under the if (pfn).
> 
> > +	if (pfn)
> > +		*pfn = local_pfn;
> > +
> > +	/* This the valid size at the specified address */
> > +	return PHYS_PFN(min_t(size_t, size, dax_size - offset));
> > +}
> > +
> 
> > +
> > +static const struct dax_operations dev_dax_ops = {
> > +	.direct_access = dev_dax_direct_access,
> > +	.zero_page_range = dev_dax_zero_page_range,
> > +	.recovery_write = dev_dax_recovery_write,
> > +};
> > +
> > +#endif /* IS_ENABLED(CONFIG_DEV_DAX_IOMAP) */
> > +
> >  struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
> >  {
> >  	struct dax_region *dax_region = data->dax_region;
> > @@ -1404,11 +1505,17 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
> >  		}
> >  	}
> >  
> 
> If we were to make this 
> 
> 	if (IS_ENABLED(CONFIG_DEV_DAX_IOMAP))
> 
> etc can we avoid the ifdef stuff above and let dead code removal deal with it?
> Might need a few stubs - I haven't tried.

Better, thanks. No stubs needed.

> 
> > +#if IS_ENABLED(CONFIG_DEV_DAX_IOMAP)
> > +	/* holder_ops currently populated separately in a slightly hacky way */
> > +	dax_dev = alloc_dax(dev_dax, &dev_dax_ops);
> > +#else
> >  	/*
> >  	 * No dax_operations since there is no access to this device outside of
> >  	 * mmap of the resulting character device.
> >  	 */
> >  	dax_dev = alloc_dax(dev_dax, NULL);
> > +#endif

Thanks!
John
diff mbox series

Patch

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 664e8c1b9930..06fcda810674 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -10,6 +10,12 @@ 
 #include "dax-private.h"
 #include "bus.h"
 
+#if IS_ENABLED(CONFIG_DEV_DAX_IOMAP)
+#include <linux/backing-dev.h>
+#include <linux/pfn_t.h>
+#include <linux/range.h>
+#endif
+
 static DEFINE_MUTEX(dax_bus_lock);
 
 #define DAX_NAME_LEN 30
@@ -1349,6 +1355,101 @@  __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
 }
 EXPORT_SYMBOL_GPL(dax_pgoff_to_phys);
 
+#if IS_ENABLED(CONFIG_DEV_DAX_IOMAP)
+
+static void write_dax(void *pmem_addr, struct page *page,
+		unsigned int off, unsigned int len)
+{
+	unsigned int chunk;
+	void *mem;
+
+	while (len) {
+		mem = kmap_local_page(page);
+		chunk = min_t(unsigned int, len, PAGE_SIZE - off);
+		memcpy_flushcache(pmem_addr, mem + off, chunk);
+		kunmap_local(mem);
+		len -= chunk;
+		off = 0;
+		page++;
+		pmem_addr += chunk;
+	}
+}
+
+static long __dev_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
+			     long nr_pages, enum dax_access_mode mode, void **kaddr,
+			     pfn_t *pfn)
+{
+	struct dev_dax *dev_dax = dax_get_private(dax_dev);
+	size_t dax_size = dev_dax_size(dev_dax);
+	size_t size = nr_pages << PAGE_SHIFT;
+	size_t offset = pgoff << PAGE_SHIFT;
+	phys_addr_t phys;
+	u64 virt_addr = dev_dax->virt_addr + offset;
+	pfn_t local_pfn;
+	u64 flags = PFN_DEV|PFN_MAP;
+
+	WARN_ON(!dev_dax->virt_addr); /* virt_addr must be saved for direct_access */
+
+	phys = dax_pgoff_to_phys(dev_dax, pgoff, nr_pages << PAGE_SHIFT);
+
+	if (kaddr)
+		*kaddr = (void *)virt_addr;
+
+	local_pfn = phys_to_pfn_t(phys, flags); /* are flags correct? */
+	if (pfn)
+		*pfn = local_pfn;
+
+	/* This the valid size at the specified address */
+	return PHYS_PFN(min_t(size_t, size, dax_size - offset));
+}
+
+static int dev_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+				    size_t nr_pages)
+{
+	long resid = nr_pages << PAGE_SHIFT;
+	long offset = pgoff << PAGE_SHIFT;
+
+	/* Break into one write per dax region */
+	while (resid > 0) {
+		void *kaddr;
+		pgoff_t poff = offset >> PAGE_SHIFT;
+		long len = __dev_dax_direct_access(dax_dev, poff,
+						   nr_pages, DAX_ACCESS, &kaddr, NULL);
+		len = min_t(long, len, PAGE_SIZE);
+		write_dax(kaddr, ZERO_PAGE(0), offset, len);
+
+		offset += len;
+		resid  -= len;
+	}
+	return 0;
+}
+
+static long dev_dax_direct_access(struct dax_device *dax_dev,
+		pgoff_t pgoff, long nr_pages, enum dax_access_mode mode,
+		void **kaddr, pfn_t *pfn)
+{
+	return __dev_dax_direct_access(dax_dev, pgoff, nr_pages, mode, kaddr, pfn);
+}
+
+static size_t dev_dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	size_t len, off;
+
+	off = offset_in_page(addr);
+	len = PFN_PHYS(PFN_UP(off + bytes));
+
+	return _copy_from_iter_flushcache(addr, bytes, i);
+}
+
+static const struct dax_operations dev_dax_ops = {
+	.direct_access = dev_dax_direct_access,
+	.zero_page_range = dev_dax_zero_page_range,
+	.recovery_write = dev_dax_recovery_write,
+};
+
+#endif /* IS_ENABLED(CONFIG_DEV_DAX_IOMAP) */
+
 struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
 {
 	struct dax_region *dax_region = data->dax_region;
@@ -1404,11 +1505,17 @@  struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
 		}
 	}
 
+#if IS_ENABLED(CONFIG_DEV_DAX_IOMAP)
+	/* holder_ops currently populated separately in a slightly hacky way */
+	dax_dev = alloc_dax(dev_dax, &dev_dax_ops);
+#else
 	/*
 	 * No dax_operations since there is no access to this device outside of
 	 * mmap of the resulting character device.
 	 */
 	dax_dev = alloc_dax(dev_dax, NULL);
+#endif
+
 	if (IS_ERR(dax_dev)) {
 		rc = PTR_ERR(dax_dev);
 		goto err_alloc_dax;